Different dataset
Different training settings, previous was dreambooth with celeb token,
New keyword







LoRA of QuarterJade (Jodi)
If you'd like to tip or request a custom LoRA - Click Here - Ko-Fi
If you like my LoRA's please leave a 5 star review, Thank you :)
1. LoRA weight : 0.6 to 1
2. Size : 512x768 or 768x768 + high res fix with 1.5x upscale. with either 8x NMKD Superscale 150000 or 4x Ultra Sharp or any others you like.
3. Optional/Recommend - use adetailer extension - for better results with further shots, input the entire positive and negative prompt into adetailer
4. See example prompts
Different dataset
Different training settings, previous was dreambooth with celeb token,
New keyword
1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.
2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim
